Achieving energy efficiency during collective communications
- Ames Lab., Ames, IA (United States)
- Iowa State Univ., Ames, IA (United States)
Energy consumption has become a major design constraint in modern computing systems. With the advent of petaflops architectures, power-efficient software stacks have become imperative for scalability. Techniques such as dynamic voltage and frequency scaling (called DVFS) and CPU clock modulation (called throttling) are often used to reduce the power consumption of the compute nodes. To avoid significant performance losses, these techniques should be used judiciously during parallel application execution. For example, its communication phases may be good candidates to apply the DVFS and CPU throttling without incurring a considerable performance loss. They are often considered as indivisible operations although little attention is being devoted to the energy saving potential of their algorithmic steps. In this work, two important collective communication operations, all-to-all and allgather, are investigated as to their augmentation with energy saving strategies on the per-call basis. The experiments prove the viability of such a fine-grain approach. They also validate a theoretical power consumption estimate for multicore nodes proposed here. While keeping the performance loss low, the obtained energy savings were always significantly higher than those achieved when DVFS or throttling were switched on across the entire application run
- Research Organization:
- Ames Lab., Ames, IA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- DOE Contract Number:
- AC02-07CH11358
- OSTI ID:
- 1132053
- Report Number(s):
- IS-J 8178
- Journal Information:
- Concurrency and Computation. Practice and Experience, Vol. 25, Issue 15; ISSN 1532-0626
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Case for Application Oblivious Energy-Efficient MPI Runtime
Strategies for Energy Efficient Resource Management of Hybrid Programming Models